CN110827966A - Regional single disease supervision system - Google Patents
Regional single disease supervision system Download PDFInfo
- Publication number
- CN110827966A CN110827966A CN201911093554.XA CN201911093554A CN110827966A CN 110827966 A CN110827966 A CN 110827966A CN 201911093554 A CN201911093554 A CN 201911093554A CN 110827966 A CN110827966 A CN 110827966A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- diagnosis
- maintenance
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 32
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 32
- 238000012423 maintenance Methods 0.000 claims abstract description 72
- 238000003745 diagnosis Methods 0.000 claims abstract description 58
- 238000000034 method Methods 0.000 claims description 33
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 230000011218 segmentation Effects 0.000 claims description 21
- 238000010801 machine learning Methods 0.000 claims description 18
- 238000002372 labelling Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000007717 exclusion Effects 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000007619 statistical method Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000037361 pathway Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000001343 mnemonic effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a regional single disease type supervision system, which comprises a basic maintenance module, a medical advice type maintenance module, a variation classification maintenance module, a form classification maintenance module, a diagnosis ICD maintenance module, a surgical diagnosis maintenance module, a professional ward corresponding maintenance module, a diagnosis knowledge base module, a diagnosis guide module, a reference document module and a single disease type supervision module, wherein: the single disease type supervision module also comprises a path maintenance unit and a path inquiry unit. The invention not only realizes information resource sharing, data exchange and statistical analysis, but also reduces the supervision cost.
Description
Technical Field
The invention relates to the technical field of medical information, in particular to a regional single disease monitoring system.
Background
The study of the combination of disease supervision and internet technology by domestic academic, media and policy documents is very little, and the existing review system has the defects of attaching importance to scientific research, thesis, economic benefit and the like, but continuously strives to perfect. Single media, specialists and the like are concerned about single disease supervision, but the technology support is still seriously lacked.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a regional single disease supervision system, which is used for solving the problems in the prior art.
According to a first aspect of the invention, a regional single disease supervision system is provided, which comprises a basic maintenance module, an advice category maintenance module, a variation classification maintenance module, a form classification maintenance module, a diagnosis ICD maintenance module, an operation diagnosis maintenance module, a professional ward corresponding maintenance module, a diagnosis knowledge base module, a diagnosis and treatment guide module, a reference document module and a single disease supervision module, wherein: the single disease type supervision module also comprises a path maintenance unit and a path inquiry unit;
the basic maintenance module is used for inputting and maintaining basic data information required by daily business, wherein the basic data information comprises diagnosis and treatment process stage information, medical advice type information, variation classification information, form classification information, diagnosis ICD information, operation diagnosis information, professional ward corresponding information, diagnosis and treatment knowledge base information, diagnosis guide information and reference document information;
the medical advice type maintenance module is used for maintaining the medical advice type, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or business requirements;
the variation classification maintenance module is used for maintaining form classification of the clinical path for use in maintaining the detail of the path, and a user can correspondingly add, modify and delete according to specific conditions or business requirements;
the form classification maintenance module is used for maintaining form classification of clinical paths for use in maintaining detailed paths, and users can correspondingly add, modify and delete according to specific conditions or business requirements;
the diagnosis ICD maintenance module is used for diagnosing the maintenance of the ICD, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or service requirements;
the operation diagnosis maintenance module is used for maintenance of operation diagnosis, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or business requirements;
the professional ward corresponding maintenance module is used for maintaining correspondence between departments and professions and is used as a basis for a doctor to select a clinical path for a patient in the department to prevent the doctor from selecting an incorrect clinical path, and a user can correspondingly add or delete the incorrect clinical path according to specific conditions or business requirements;
the diagnosis and treatment knowledge base module is used for prestoring clinical disease diagnosis and treatment knowledge, and a user can correspondingly check and maintain according to specific conditions or business requirements;
the diagnosis and treatment guide module is used for prestoring clinical disease diagnosis knowledge, and a user can correspondingly check and maintain according to specific conditions or business requirements;
the reference module is used for storing and sharing documents in the working aspect;
the single disease type supervision module is used for storing path information required by daily business so as to meet the requirement of clinical path information management;
the route maintenance unit is used for maintaining basic route information, wherein the basic route information comprises a route name, an applicable object, activity time, diagnosis basis, a treatment scheme, an admission standard, an exclusion condition, discharge assessment, variation, complications, content maintenance, medical advice maintenance, display and template management;
and the path inquiry unit is used for checking the maintained path information.
Further, the reference module also comprises a preset part or all of the reference module to be viewed, modified and/or deleted by a user with preset authority.
Further, the method also comprises the step of screening and viewing information of single or combined conditions through the path code, the path name, the release state, the standard, the professional and the logout state in the path inquiry unit.
Further, the profile information includes a classification knowledge-graph to classify the information it includes.
Further, the method also comprises the following steps of constructing the classification knowledge graph in advance:
extracting basic data information, and inducing the information by experts to form an entity and a relation reference rule base of various information;
training a big data machine model based on an expert labeling rule and a machine learning rule by a big data neural network word segmentation method;
and pre-labeling the unmarked information by using the trained big data machine model to form a classification knowledge map.
Further, the big data neural network word segmentation method refers to: a big data analysis method, word segmentation rules of a dictionary database, and a neural network clustering and classifying method are integrated.
Further, the big data neural network word segmentation method for training the big data machine model based on the rules labeled by experts and the machine learning rules includes:
receiving information;
segmenting words based on segmentation rules of a dictionary database;
labeling experts;
analyzing big data;
neural network machine learning;
clustering by a neural network;
classifying a neural network;
and outputting a classification result.
Further, the big data neural network word segmentation method trains a big data machine model based on the rules labeled by experts and the machine learning rules, and further includes:
and combining redundant nodes in the information and deleting useless nodes.
Further, the big data neural network word segmentation method trains a big data machine model based on the rules labeled by experts and the machine learning rules, and further includes:
and combining redundant characters and words in the information and deleting useless characters and words.
Further, the machine learning rule is set in a CRF model, a BilSTM model, or a BERT model.
Compared with the prior art, the invention has the beneficial effects that:
the invention not only realizes information resource sharing, data exchange and statistical analysis, but also reduces the supervision cost.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic structural diagram of a regional single disease monitoring system according to a first embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
In some of the flows described in the present specification and claims and in the above figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, with the order of the operations being indicated as 101, 102, etc. merely to distinguish between the various operations, and the order of the operations by themselves does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and are not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Example one
As shown in fig. 1, an embodiment of the present invention provides a regional single disease monitoring system, which includes a basic maintenance module, a medical advice category maintenance module, a variation classification maintenance module, a form classification maintenance module, a diagnosis ICD maintenance module, a surgical diagnosis maintenance module, a professional disease area corresponding maintenance module, a diagnosis knowledge base module, a diagnosis guideline module, a reference module, and a single disease monitoring module, wherein: the single disease type supervision module also comprises a path maintenance unit and a path inquiry unit;
the basic maintenance module is used for inputting and maintaining basic data information required by daily business, wherein the basic data information comprises diagnosis and treatment process stage information, medical advice type information, variation classification information, form classification information, diagnosis ICD information, operation diagnosis information, professional ward corresponding information, diagnosis and treatment knowledge base information, diagnosis guide information and reference document information;
the basic maintenance module is mainly used for maintaining main links of a hospitalization diagnosis and treatment process, namely diagnosis and treatment process stages and diagnosis and treatment activities contained in each diagnosis and treatment process stage. The user can perform corresponding adding, modifying and deleting work according to specific situations or service requirements. The basic maintenance module has the design characteristics that: the data is relatively stable and does not change frequently.
The contents and descriptions in the basic maintenance module are as follows:
and (3) encoding: the system automatically generates, defaults to two digits, can only be represented by the numbers 0-9, and cannot be null.
Name: the maximum of 50 characters can be Chinese characters, numbers or English letters; cannot be empty; cannot be repeated.
Mnemonic code: and automatically generating according to the name.
Logout: in a certain diagnosis and treatment process stage, the user does not want to use the system, does not want to delete the system or cannot delete the system, and can log the system out.
After all the information is input, click on "save (S)", or press "ctrl + S" key, and save is performed.
The system comprises a medical advice type maintenance module, a data processing module and a data processing module, wherein the medical advice type maintenance module is used for maintaining medical advice types, and a user can correspondingly add, modify and delete according to specific conditions or business requirements;
the medical order type maintenance module is mainly used for maintaining the medical order types, and a user can correspondingly add, modify and delete according to specific conditions or business requirements. The data is relatively stable and does not change frequently.
The variation classification maintenance module is used for maintaining form classification of the clinical path and is used when the path detail is maintained, and a user can correspondingly add, modify and delete according to specific conditions or business requirements;
the form classification maintenance module is used for maintaining form classification of the clinical path and is used when the path detail is maintained, and a user can correspondingly add, modify and delete according to specific conditions or business requirements;
the diagnosis ICD maintenance module is used for diagnosing the maintenance of the ICD, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or service requirements;
the operation diagnosis maintenance module is used for maintaining operation diagnosis, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or business requirements;
the professional ward corresponding maintenance module is used for maintaining correspondence between departments and professions and is used as a basis for a doctor to select a clinical path for a patient in the departments to prevent the doctor from selecting an incorrect clinical path, and a user can correspondingly add or delete according to specific conditions or business requirements;
the diagnosis and treatment knowledge base module is used for prestoring clinical disease diagnosis and treatment knowledge, and a user can correspondingly check and maintain according to specific conditions or business requirements;
the diagnosis and treatment guide module is used for prestoring clinical disease diagnosis knowledge, and a user can correspondingly check and maintain according to specific conditions or business requirements;
the reference module is used for storing and sharing documents in the aspect of work;
the single disease type supervision module is used for storing path information required by daily business so as to meet the requirement of clinical path information management;
the single disease type supervision module is used for establishing path information required by daily business to meet the requirement of clinical path information management before formally using the single disease type supervision system to process the daily business.
The route maintenance unit is used for maintaining basic route information, wherein the basic route information comprises a route name, an applicable object, activity time, diagnosis basis, a treatment scheme, an admission standard, an exclusion condition, discharge assessment, variation, complications, content maintenance, medical advice maintenance, display and template management;
path name: the maximum of 50 characters can be Chinese characters, numbers or English letters; cannot be empty; cannot be repeated.
The path name includes path code: default to 10 bits, the system automatically generates. The first 2 bits represent the standard; 4-7 bits are professional coding of the path; the last 3 bits are the sequential code.
The standard is as follows: the standard is divided into three types: the clinical pathway released by the Ministry of health is 'national standard-GB'; the clinical pathway released by the health hall is 'provincial-DB'; the hospital's own clinical pathway is "hospital standard-QB". And cannot be empty.
And the path query unit is used for checking the maintained path information.
And screening and viewing information of single or combined conditions through the path code, the path name, the release state, the standard, the professional and the logout state in the path query unit.
The invention also comprises the following steps of pre-constructing the classification knowledge graph:
extracting basic data information, and inducing the information by experts to form an entity and a relation reference rule base of various information;
training a big data machine model based on an expert labeling rule and a machine learning rule by a big data neural network word segmentation method;
the big data neural network word segmentation method is as follows: a big data analysis method, word segmentation rules of a dictionary database, and a neural network clustering and classifying method are integrated.
The big data neural network word segmentation method for training a big data machine model based on an expert labeling rule and a machine learning rule comprises the following steps:
receiving information;
segmenting words based on segmentation rules of a dictionary database;
labeling experts;
analyzing big data;
neural network machine learning;
clustering by a neural network;
classifying a neural network;
and outputting a classification result.
The big data neural network word segmentation method trains a big data machine model based on the rules marked by experts and machine learning rules, and further comprises the following steps:
and combining redundant nodes in the information and deleting useless nodes.
The big data neural network word segmentation method trains a big data machine model based on the rules marked by experts and machine learning rules, and further comprises the following steps:
and combining redundant characters and words in the information and deleting useless characters and words.
The machine learning rules are set in a CRF model, a BilSTM model, or a BERT model.
CRF is a special case of a Markov random field, which assumes that there are only two variables X and Y in the Markov random field, X generally being given and Y generally being our output given X.
CRF with X and Y having the same structure constitutes a random field of the linear chain element.
Mathematical language description of CRF: let X and Y be random variables, and P (Y | X) be the conditional probability distribution of Y given X, and if the random variable Y constitutes a Markov random field, then the conditional probability distribution P (Y | X) is called a conditional random field. (discriminant model)
Mathematical definition of line-CRF: let X be X1,X2,…,Xn，Y＝Y1,Y2,…,YnRandom variable sequences, each represented by a linear chain, the conditional probability distribution P (Y | X) of a random variable Y, given a random variable sequence X, constitutes a conditional random field, i.e. satisfying markov property: p (Y)i|X,Y1,Y2,…,Yn)＝P(Yi|X,Yi-1,…,Yi+1) P (Y | X) is called the random field of the linear chain element.
LSTM is known collectively as Long Short-Term Memory, which is one of RNN (Current Neural network). LSTM is well suited for modeling time series data, such as text data, due to its design features. BilSTM is an abbreviation of Bi-directional Long Short-Term Memory, and is formed by combining forward LSTM and backward LSTM. Both are often used to model context information in natural language processing tasks.
The LSTM model is formed by the input word X at time ttCell state CtTemporary cell state
Hidden layer state htForgetting door ftMemory door itOutput gate otAnd (4) forming. The calculation process of the LSTM can be summarized as that information useful for the calculation at the subsequent moment is transmitted by forgetting and memorizing new information in the cell state, while useless information is discarded and is output at each time stepOut of hidden layer state htWherein the forgetting, memorizing and outputting are based on the hidden layer state h passing the last momentt-1And current input XtCalculated forgetting door ftMemory door itOutput gate otTo control.
First, this model is very deep, 12 layers and not wide (wide), the middle layer is only 1024, while the previous Transformer model middle layer is 2048. This again seems to justify a view of computer image processing-deep narrow is better than shallow wide models.
Secondly, mlm (masked Language model), using words on both left and right sides, the core of this model is the focusing mechanism, and for a statement, multiple focus points can be enabled at the same time, and it is not necessary to be limited to the serial processing of the sequence from the front to the back or from the back to the front. Not only the structure of the model needs to be correctly selected, but also the parameters of the model need to be correctly trained, so that the model can be guaranteed to accurately understand the semantics of the sentence. BERT takes two steps in an attempt to correctly train the parameters of the model. The first step is to cover 15% of the vocabulary in an article, and let the model predict the covered words omnidirectionally according to context. Assuming there are 1 million articles, each with an average of 100 words, randomly covering 15% of the words, the model's task is to correctly predict these 15 million covered words. The parameters of the Transformer model are initially trained by omni-directionally predicting the covered vocabulary.
Then, the second step is used to continue training the parameters of the model. For example, from the 1 ten thousand articles, 20 ten thousand pairs of sentences were picked, for a total of 40 ten thousand sentences. When the sentence pairs are selected, 210 ten thousand pairs of sentences are two continuous contextual sentences, and the other 210 ten thousand pairs of sentences are not continuous sentences. The Transformer model is then asked to identify the 20 ten thousand pairs of statements, which are contiguous and which are not.
These two training steps are combined and called pre-training. The Transformer model after training, including its parameters, is a generic language characterization model of a Masked Language Model (MLM) to overcome the above-mentioned unidirectional limitation.
The latest record of 11 natural language processing tasks that BERT has currently refreshed includes: the GLUE benchmark was pushed to 80.4% (7.6% absolute improvement), the MultiNLI accuracy reached 86.7% (5.6% absolute improvement), and the SQuAD v1.1 question-answer test F1 score record was refreshed to 93.2 points (1.5 points absolute improvement), exceeding human performance by 2.0 points.
And pre-labeling the unmarked information by using the trained big data machine model to form a classification knowledge map.
In the embodiments provided in the present application, it should be understood that the disclosed systems, devices, modules and/or units may be implemented in other manners. For example, the above-described method embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. The utility model provides a regional single disease kind supervisory systems, its characterized in that includes basic maintenance module, doctor's advice classification maintenance module, variation classification maintenance module, form classification maintenance module, diagnosis ICD maintenance module, operation diagnosis maintenance module, professional ward correspond maintenance module, diagnose knowledge base module, diagnose guide module, reference module, single disease kind supervisory module, wherein: the single disease type supervision module also comprises a path maintenance unit and a path inquiry unit;
the basic maintenance module is used for inputting and maintaining basic data information required by daily business, wherein the basic data information comprises diagnosis and treatment process stage information, medical advice type information, variation classification information, form classification information, diagnosis ICD information, operation diagnosis information, professional ward corresponding information, diagnosis and treatment knowledge base information, diagnosis guide information and reference document information;
the medical advice type maintenance module is used for maintaining the medical advice type, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or business requirements;
the variation classification maintenance module is used for maintaining form classification of the clinical path for use in maintaining the detail of the path, and a user can correspondingly add, modify and delete according to specific conditions or business requirements;
the form classification maintenance module is used for maintaining form classification of clinical paths for use in maintaining detailed paths, and users can correspondingly add, modify and delete according to specific conditions or business requirements;
the diagnosis ICD maintenance module is used for diagnosing the maintenance of the ICD, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or service requirements;
the operation diagnosis maintenance module is used for maintenance of operation diagnosis, and a user can perform corresponding adding, modifying and deleting work according to specific conditions or business requirements;
the professional ward corresponding maintenance module is used for maintaining correspondence between departments and professions and is used as a basis for a doctor to select a clinical path for a patient in the department to prevent the doctor from selecting an incorrect clinical path, and a user can correspondingly add or delete the incorrect clinical path according to specific conditions or business requirements;
the diagnosis and treatment knowledge base module is used for prestoring clinical disease diagnosis and treatment knowledge, and a user can correspondingly check and maintain according to specific conditions or business requirements;
the diagnosis and treatment guide module is used for prestoring clinical disease diagnosis knowledge, and a user can correspondingly check and maintain according to specific conditions or business requirements;
the reference module is used for storing and sharing documents in the working aspect;
the single disease type supervision module is used for storing path information required by daily business so as to meet the requirement of clinical path information management;
the route maintenance unit is used for maintaining basic route information, wherein the basic route information comprises a route name, an applicable object, activity time, diagnosis basis, a treatment scheme, an admission standard, an exclusion condition, discharge assessment, variation, complications, content maintenance, medical advice maintenance, display and template management;
and the path inquiry unit is used for checking the maintained path information.
2. The system of claim 1, wherein the reference module further comprises a user with preset authority to view, modify and/or delete part or all of the reference.
3. The system according to claim 1, further comprising a screening and viewing information of single or combined condition through the path code, path name, release status, standard, professional, logout status in the path query unit.
4. The system of regional monomial surveillance of claim 1, wherein the base information comprises a classification knowledgegraph to classify information it comprises.
5. The system of regional individual disease surveillance of claim 4, further comprising, prior to construction of the classification knowledgebase:
extracting basic data information, and inducing the information by experts to form an entity and a relation reference rule base of various information;
training a big data machine model based on an expert labeling rule and a machine learning rule by a big data neural network word segmentation method;
and pre-labeling the unmarked information by using the trained big data machine model to form a classification knowledge map.
6. The system of claim 5, wherein the big data neural network word segmentation method is that: a big data analysis method, word segmentation rules of a dictionary database, and a neural network clustering and classifying method are integrated.
7. The system of claim 5, wherein the big data neural network word segmentation method, training big data machine model based on expert labeled rules and machine learning rules, comprises:
receiving information;
segmenting words based on segmentation rules of a dictionary database;
labeling experts;
analyzing big data;
neural network machine learning;
clustering by a neural network;
classifying a neural network;
and outputting a classification result.
8. The system of claim 7, wherein the big data neural network word segmentation method trains the big data machine model based on expert labeled rules and machine learning rules, further comprising:
and combining redundant nodes in the information and deleting useless nodes.
9. The system of claim 7, wherein the big data neural network word segmentation method trains the big data machine model based on expert labeled rules and machine learning rules, further comprising:
and combining redundant characters and words in the information and deleting useless characters and words.
10. The system of any of claims 4-9, wherein the machine learning rules are provided in a CRF model, a BiLSTM model, or a BERT model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911093554.XA CN110827966A (en) | 2019-11-11 | 2019-11-11 | Regional single disease supervision system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911093554.XA CN110827966A (en) | 2019-11-11 | 2019-11-11 | Regional single disease supervision system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110827966A true CN110827966A (en) | 2020-02-21 |
Family
ID=69553716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911093554.XA Pending CN110827966A (en) | 2019-11-11 | 2019-11-11 | Regional single disease supervision system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110827966A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380345A (en) * | 2020-11-20 | 2021-02-19 | 山东省计算中心（国家超级计算济南中心） | COVID-19 scientific literature fine-grained classification method based on GNN |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104820724A (en) * | 2015-05-29 | 2015-08-05 | 蓝舰信息科技南京有限公司 | Method for obtaining prediction model of knowledge points of text-type education resources and model application method |
| CN110377755A (en) * | 2019-07-03 | 2019-10-25 | 江苏省人民医院（南京医科大学第一附属医院） | Reasonable medication knowledge map construction method based on medicine specification |
-
2019
- 2019-11-11 CN CN201911093554.XA patent/CN110827966A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104820724A (en) * | 2015-05-29 | 2015-08-05 | 蓝舰信息科技南京有限公司 | Method for obtaining prediction model of knowledge points of text-type education resources and model application method |
| CN110377755A (en) * | 2019-07-03 | 2019-10-25 | 江苏省人民医院（南京医科大学第一附属医院） | Reasonable medication knowledge map construction method based on medicine specification |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380345A (en) * | 2020-11-20 | 2021-02-19 | 山东省计算中心（国家超级计算济南中心） | COVID-19 scientific literature fine-grained classification method based on GNN |
| CN112380345B (en) * | 2020-11-20 | 2022-03-29 | 山东省计算中心（国家超级计算济南中心） | COVID-19 scientific literature fine-grained classification method based on GNN |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Suresh et al. | A framework for understanding sources of harm throughout the machine learning life cycle | |
| Wilson et al. | Modeling binary correlated responses using SAS, SPSS and R | |
| Sulieman et al. | Classifying patient portal messages using Convolutional Neural Networks | |
| Basu Roy et al. | Dynamic hierarchical classification for patient risk-of-readmission | |
| JP6916310B2 (en) | Human-participatory interactive model training | |
| Kabir et al. | DEPTWEET: A typology for social media texts to detect depression severities | |
| US20210182606A1 (en) | System and Method for Labeling Medical Data to Generate Labeled Training Data | |
| Marmolejo‐Ramos et al. | Distributional regression modeling via generalized additive models for location, scale, and shape: An overview through a data set from learning analytics | |
| Karmakar | Classifying medical notes into standard disease codes using machine learning | |
| CN110827966A (en) | Regional single disease supervision system | |
| Zaghir et al. | Real-world patient trajectory prediction from clinical notes using artificial neural networks and UMLS-based extraction of concepts | |
| Zhang et al. | Applying artificial intelligence methods for the estimation of disease incidence: the utility of language models | |
| Ramesh et al. | A frame work for classification of multi class medical data based on deep learning and Naive Bayes classification model | |
| Karmalkar et al. | Artificial intelligence-driven approach for patient-focused drug development | |
| Abu Lekham et al. | Multi-label text mining to identify reasons for appointments to drive population health analytics at a primary care setting | |
| Lutz et al. | Topic Modeling as an evaluation basis in literature research–A proposal for a new literature review method for machine-assisted source evaluation using the example of anthropology. | |
| Suresh et al. | A Framework of Potential Sources of Harm Throughout the Machine Learning Life Cycle | |
| Bonnerud | Write like me: Personalized natural language generation using transformers | |
| CN117194604B (en) | Intelligent medical patient inquiry corpus construction method | |
| Jones | Prediction and analysis of degree of suicidal ideation in online content | |
| CN117497111B (en) | System for realizing disease name standardization and classification based on deep learning | |
| Cook | The mathematics of clinical diagnosis: cognitively-inspired computational psychiatry | |
| Miller | Clinical ambiguity in the intelligent machine era (treats breaks and discharges) | |
| Reddy et al. | A Novel Method for Enhancing Accuracy in Mining Twitter Data Using Naive Bayes over Logistic Regression | |
| Prabhakar et al. | Diagnostic Code Group Prediction by Integrating Structured and Unstructured Clinical Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200221 |
|
| RJ01 | Rejection of invention patent application after publication |